de en es ja ko ru zh

finary-mcp

Name: finary-mcp
Author: adagues

by adagues

Overview Schema Source Related Servers Discussions Admin

Python

Local

finary-mcp

意図的に読み取り専用の Model Context Protocol サーバーであり、Finary 向けに、非公式の finary-uapi クライアント上に構築されています。

[!WARNING] このプロジェクトは Finary とは独立しており、Finary による承認、サポート、保守はされていません。finary-uapi を通じて非公開・未文書化のエンドポイントに依存しており、どちらのプロジェクトも予告なく壊れる可能性があります。これは財務、税金、法律、投資のアドバイスではありません。

安全性モデル

finary-mcp は意図的に、範囲を絞った読み取り専用アダプターです：

プロフィール、組織、機関、ポートフォリオ、取引のクエリのみを公開します。
ログイン、アカウントインポート、作成、更新、削除、振替、取引、または汎用 CLI ツールはありません。
シェルを介さず、固定の許可リストから finary-uapi コマンドを構築します。
フィルタ値は実行前に検証されます。
リクエストが失敗した場合、上流の stdout/stderr を返しません。上流のログインフローがセッション情報を出力する可能性があるためです。
状態ディレクトリは明示的です（FINARY_MCP_STATE_DIR）。任意の作業ディレクトリからトークンを探すことはありません。

これにより、MCP を通じた偶発的な書き込みが減ります。ただし、別のプロセスがセッションファイルを読み取れる場合、マシンを安全にすることはできません。信頼できるアカウントとプロフィールでのみサーバーを実行してください。

認証に関する重要な注意

「読み取り専用」とは、Finary のポートフォリオデータに関するものです。finary-uapi はリクエストの前に Clerk セッションを更新し、jwt.json を書き換える可能性があります。そのため、MCP ツールが Finary のデータを変更することはないものの、プライベート状態ディレクトリはローカルサービスアカウントから書き込み可能な状態を保つ必要があります。サーバーがそのファイル、Cookie、子プロセスの診断情報を返すことはありません。

finary-uapi は推移的依存関係として GPL-2.0 の fuzzywuzzy も取り込みます。配布またはデプロイを予定している場合は、上流の依存関係グラフとライセンスへの影響を確認してください。

Related MCP server: monarch

前提条件

Python 3.10+。
finary-uapi によってすでに作成されたローカルの Finary セッション。
jwt.json と localCookiesMozilla.txt の両方を含むプライベートディレクトリ。ディレクトリのモードは 0700、ファイルのモードは 0600。

サーバー自体は Google OAuth をサポートしていません。finary-uapi がサポートする認証プロセスに従って、ローカルセッションを作成または更新してください。パスワード、TOTP コード、JWT、Cookie のエクスポート、セッションファイルをエージェント、リポジトリ、課題トラッカー、チャットに送信しないでください。

インストール

python -m venv .venv
. .venv/bin/activate
pip install finary-mcp

チェックアウトからの開発の場合：

pip install -e '.[dev]'
pytest -q

MCP ホストを設定する

FINARY_MCP_STATE_DIR に、Finary セッションを保持するディレクトリを設定します。finary-uapi が別の仮想環境にインストールされている場合は、FINARY_UAPI_PYTHON にその環境の Python 実行ファイルを設定します。

汎用 stdio 設定の例：

{
  "mcpServers": {
    "finary": {
      "command": "/path/to/finary-mcp/.venv/bin/finary-mcp",
      "env": {
        "FINARY_MCP_STATE_DIR": "/private/path/to/finary-state",
        "FINARY_UAPI_PYTHON": "/path/to/finary-uapi/.venv/bin/python"
      }
    }
  }
}

絶対パスを使用してください。状態ディレクトリはプライベートデータであり、決してコミットしてはいけません。同梱の .gitignore は既知のセッションファイルを除外します。

Hermes Agent の例

mcp_servers:
  finary:
    command: /path/to/finary-mcp/.venv/bin/finary-mcp
    env:
      FINARY_MCP_STATE_DIR: /private/path/to/finary-state
      FINARY_UAPI_PYTHON: /path/to/finary-uapi/.venv/bin/python
    tools:
      include:
        - finary_me
        - finary_organizations
        - finary_institution_connections
        - finary_portfolio
        - finary_transactions

資格情報を公開された設定ファイルにコピーするのではなく、Hermes の MCP/設定ワークフローを通じてこれを追加してください。サーバーを追加した後は、ツール検出が再実行されるように Hermes プロセスを再起動してください。

ツール

Tool	読み取り専用の目的
`finary_me`	認証されたプロフィールを読み取ります。
`finary_organizations`	アクセス可能な Finary 組織を一覧表示します。
`finary_institution_connections`	金融機関の接続を一覧表示します。
`finary_portfolio`	許可されたポートフォリオクラス（投資、有価証券、暗号資産、fonds euro、SCPI、不動産、保有口座）を読み取ります。
`finary_transactions`	当座、投資、またはクレジットの取引を、ページネーションと日付/アカウントフィルタ付きで読み取ります。

依存関係: `finary-uapi`

このプロジェクトは、Finary の API を再実装するものではなく、アダプターです。lasconic/finary _uapi プロジェクトの finary-uapi CLI を呼び出します。そのパッケージは現在 pyproject.toml で finary-uapi>=0.2.3,<0.3 として宣言されています。

この依存関係は、未文書化の Finary エンドポイントを使用し、ローカルセッションを保持します。このサーバーを使用する前に、そのソースとライセンスを確認してください。上流のアップグレードが必要な場合は、まず別の環境でテストし、互換性のあるバージョンをここに固定してください。

開発

pytest -q
python -m build

テストは実際の Finary アカウントを使用せず、セッションファイルを作成してはいけません。公開する前に、ステージングされたファイルに jwt.json、localCookiesMozilla.txt、資格情報、メールアドレス、Cookie、トークンが含まれていないかスキャンしてください。

ライセンス

MIT。LICENSE を参照してください。

Available Tools

5 tools

finary_institution_connectionsA

List connected financial institutions and their connection status.

Name	Required	Description	Default
No parameters

TDQS

A3.6/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must carry the full burden of behavioral disclosure, but it only states the action. It does not mention read-only nature, response format, pagination, or any caveats about connection status semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, concise sentence with no filler. The key action and object are front-loaded, making it easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter listing tool, the description is reasonably complete. However, without an output schema or any mention of response fields (e.g., what 'status' values look like), an agent lacks some context about the expected result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero parameters, so the baseline is 4. The description correctly adds no unnecessary parameter detail, and there is nothing to compensate for since the schema is trivially complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and a clear resource ('connected financial institutions') along with a relevant detail ('connection status'). It clearly distinguishes this tool from siblings like finary_portfolio or finary_transactions by focusing on institution connections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no indication of when to use this tool versus alternatives, nor any exclusions or prerequisites. An agent is left to infer the use case from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

finary_meA

Read the authenticated Finary profile. Does not modify Finary.

Name	Required	Description	Default
No parameters

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It explicitly states 'Does not modify Finary', which is a key behavioral trait for a read operation. It does not mention return format or errors, but for a simple profile read this is acceptable. Adding 'Read' reinforces the non-destructive nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the core action and a clear non-modification statement. No fluff or redundancy. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only tool, the description covers the essential purpose and side-effect behavior. It does not explicitly state return data format (no output schema exists), but an agent can reasonably infer it returns the profile object. Minor gap, but adequate for this simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so the baseline is 4. The description does not need to explain parameters because none exist. Schema coverage is 100% vacuously, and no parameter documentation is required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'Read' with a specific resource, 'authenticated Finary profile', and explicitly states it does not modify. This distinguishes it from sibling tools like finary_transactions or finary_portfolio without ambiguity. The purpose is clear and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates the tool retrieves the user's own Finary profile, which sets clear context for when it applies. However, it does not explicitly mention alternatives or conditions for when not to use it, though the resource is so distinct that usage is implied. Missing explicit routing to siblings, but adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

finary_organizationsB

List Finary organizations available to the authenticated user.

Name	Required	Description	Default
No parameters

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'List' and mentions 'authenticated user', which implies a read-only operation but does not state side effects, rate limits, response format, or any required authentication details. The lack of explicit behavioral context is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with no redundant words. It is perfectly concise and front-loads the core action, making it efficient for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (no parameters, no output schema), the description is minimal but lacks important context. It does not explain pagination, what an 'organization' entails, or how this relates to sibling tools. For a tool with no annotations, more behavioral and situational details are needed for complete understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so schema coverage is trivially 100%. The description adds nothing about parameters because none exist, but the baseline for zero-parameter tools is a 4, and the tool meets this baseline as there is nothing to clarify.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the function: 'List Finary organizations' with the scope 'available to the authenticated user.' The verb 'list' is specific and the resource is clear. It doesn't explicitly differentiate from sibling tools, but the name and context make the intent obvious, so it earns a 4.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like finary_portfolio or finary_transactions. An agent is left to infer usage from the name and generic phrasing. There are no exclusions or specific scenarios mentioned, so this dimension is weakly addressed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

finary_portfolioB

Read a portfolio class: investments, securities, cryptos, fonds_euro, scpis, real_estates, or holdings_accounts.

Name	Required	Description	Default
`org_id`	No
`asset_type`	No		investments

TDQS

B3.4/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the verb 'Read', implicitly indicating a non-mutating operation, but it does not mention permissions, rate limits, return format, or any side effects. The list of asset types adds domain context but not behavioral transparency. This is a significant gap for a tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no unnecessary words. The verb is front-loaded, and the enumeration of asset types is compact and informative. Every part earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema and no annotations, the description should explain what the tool returns and any other usage context, but it does not. It omits any mention of the return structure, error handling, or the org_id parameter, which is essential to know when calling the tool. The enumeration of asset types covers only part of the invocation requirements, leaving the definition incomplete for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate for parameter meaning. It explicitly lists the valid values for asset_type, which is useful and goes beyond the schema (where no descriptions exist). However, it completely ignores org_id, leaving its purpose and usage undocumented. The partial compensation leads to a middling score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Read') applied to a well-defined resource ('portfolio class'), and enumerates all valid asset types (investments, securities, cryptos, etc.), making the tool's purpose unambiguous. It naturally distinguishes itself from sibling tools by naming a resource category not covered by any sibling (e.g., me, organizations, transactions).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading portfolio holdings of a given asset type, but it provides no explicit guidance on when to choose this tool over siblings. Since siblings are clearly different domains (me, organizations, connections, transactions), the context is somewhat clear, but the description does not explicitly state scenarios or exclusions, so it remains at the 'implied' level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

finary_transactionsB

Read transactions for checking, investment, or credit accounts with optional filters.

Name	Required	Description	Default
`page`	No
`query`	No
`marked`	No
`account`	No
`perpage`	No
`end_date`	No
`start_date`	No
`institution`	No
`account_type`	Yes

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only states 'read', which implies a non-mutating operation, but it does not disclose pagination semantics, filter behavior, response structure, or any side effects. For a tool with 9 parameters, this is insufficient behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, which is concise but arguably too sparse for a tool with 9 parameters. It front-loads the core purpose, but lacks structure to organize the various optional filters, making it under-specified rather than appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters, no output schema, and no annotations, the description is incomplete for an agent to call the tool correctly. It does not explain date formats, pagination behavior, query syntax, or how filters interact, leaving too much to guesswork.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only generically mentions 'optional filters' and names account types, which maps loosely to the 'account_type' parameter, but it does not explain any of the other parameters (page, query, marked, account, perpage, dates, institution). The added value over the raw schema is minimal.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'read', the resource 'transactions', and scopes to specific account types (checking, investment, credit). This distinguishes it from sibling tools that deal with user, org, connections, and portfolio data, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies this is the tool for transaction data, and since no sibling tool covers transactions, the usage context is evident. It does not explicitly mention alternatives, but given the sibling set, the division of responsibility is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

5 tool updatesv0.1.0Aug 27, 2026
- First observedfinary_institution_connections
- First observedfinary_me
- First observedfinary_organizations
- First observedfinary_portfolio
- First observedfinary_transactions

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored 2026-08-27 01:00 across 5 tools

Disambiguation5/5

Each tool addresses a clearly distinct domain: user profile, organizations, institution connections, portfolio classes, and transactions. No overlap in purpose, and the descriptions make the boundaries obvious.

Naming Consistency5/5

All tools use a consistent 'finary_' prefix followed by a descriptive noun (me, organizations, institution_connections, portfolio, transactions). The naming pattern is uniform and predictable.

Tool Count5/5

Five tools is well-scoped for a read-only financial data API. Each tool covers a major data category without redundancy, and the count is neither sparse nor bloated.

Completeness4/5

The surface covers the core read operations for a personal finance platform: user, orgs, connections, portfolio, and transactions. Minor gaps exist, such as no detailed per-asset breakdown beyond portfolio class, but the essential workflows are supported.

Maintenance

ActivityStale

ResponsivenessNo issues

Resources

Related MCP Connectors

FinchOAuth
ch.fjnch
Read-only access to your Finch finances: accounts, transactions, spending, net worth, goals.
Finance
1
https://api.fjnch.ch/mcp
Fillfolio MCPOAuth
com.fillfolio
Read-only Fillfolio portfolios, holdings, cash, liabilities, activity, spending and budgets.
Finance
1
https://fillfolio.com/api/mcp
Genie Expense TrackerOAuth
io.github.osamaadam
Read-only access to Genie accounts, transactions, investments, and financial summaries.
Finance
1
https://genie-mobile.duckdns.org/mcp
Synci AOAuth
io.synci
Read-only access to your bank, investment, and crypto accounts: balances, transactions, holdings.
Finance
52
https://api.synci.io/mcp

Related MCP Servers

questrade-mcp
Finance Research & Data
agustinsacco
A
license
B
quality
C
maintenance
Enables read-only access to Questrade accounts, portfolios, market data, transactions, technical analysis, and order history through MCP.
Updated 2 months ago (2026-09-15 17:57 UTC)
11
MIT
monarch
Finance
simplemind-dev
A
license
Not graded
quality
A
maintenance
Enables read-only access to Monarch Money financial data, including accounts, transactions, cash flow, spending, and income, via MCP, with secure local credential storage.
Updated a month ago (2026-10-03 16:00 UTC)
1
MIT
Fillfolio MCPofficial
Finance Data Platforms
fillfolio
A
license
Not graded
quality
B
maintenance
Enables read-only access to a Fillfolio account's normalized portfolio data, including net worth, holdings with cost basis, cash and liabilities, activity, and exact asset details, plus optional bank spending summaries, transactions, and budgets for eligible accounts. Clients can query stored data only — they cannot trade, move money, modify holdings, or access credentials.
Updated 15 days ago (2026-10-17 08:50 UTC)
9 npm
MIT
LunchMoney MCP Server
Finance Cryptocurrency
Margaux0469
A
license
Not graded
quality
A
maintenance
Enables AI assistants and other MCP clients to access and manage personal finance data, including transactions, categories, tags, budgets, recurring items, accounts, crypto, and balance history through the provider's API.
Updated 12 days ago (2026-10-20 05:03 UTC)
22 npm
MIT

finary-mcp

安全性モデル

認証に関する重要な注意

前提条件

インストール

MCP ホストを設定する

Hermes Agent の例

ツール

依存関係: finary-uapi

開発

ライセンス

Available Tools

Tool Schema Changelog

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Fillfolio MCPofficial

依存関係: `finary-uapi`